app.py

import asyncio
from ollama import AsyncClient
import streamlit as st

async def chat(prompt):
    message = {'role': 'user', 'content': prompt}
    async for part in await AsyncClient().chat(model='smollm:135m', messages=[message], stream=True):
        yield part['message']['content']

async def get_full_response(prompt):
    response = ""
    async for part in chat(prompt):
        response += part
    return response

def main():
    st.title("MySQL with Llama-3")
    prompt = st.text_input("Enter your prompt:")

    if st.button("Generate"):
        if prompt:
            with st.spinner("Generating response..."):
                full_response = asyncio.run(get_full_response(prompt))
                st.write(full_response)

if __name__ == '__main__':
    main()